AI Paper Atlas

Research map / Continual learning / Online and replay-based

HLML-SNN:Fast Continual Learning in Spiking Neural Networks Achieved via Hebbian Learning-Driven Meta-Learning

Jiangshuai Xu, Peiyun Xue, Jiacheng Song, Xuhui Huang, Qingshan Hou

AAAI 2026 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add meta-learning to Hebbian learning (ablation)HLML-SNN · split-CIFAR10average accuracy (%): 52.8 -> 93.1Improved
add meta-learning to Hebbian learning (ablation)HLML-SNN · 10-split-CIFAR100average accuracy (%): 9.9 -> 90.2Improved
use Hebbian learning instead of standard gradient descent in inner loop (ablation)HLML-SNN · split-CIFAR10 / 10-split-CIFAR100training time: 3 to 5 times fasterImproved
use Hebbian learning instead of standard gradient descent in inner loop (ablation)HLML-SNN · split-CIFAR10 / 10-split-CIFAR100average accuracy (%)No clear effect
increase SNN time steps from 4 to 10 (ablation)HLML-SNN · 10-split-TinyImageNet (N)average accuracy (%): 78.9 -> 80.1Improved
increase SNN time steps from 4 to 10 (ablation)HLML-SNN · 10-split-CIFAR100training time (s): 9.54 -> 22.02Hurt
increase SNN time steps from 2 to 4 (ablation)HLML-SNN · split-CIFAR10average accuracy (%): 91.7 -> 93.1Improved
lower meta learning rate from 1e-2 to 1e-4 (ablation)HLML-SNN · split-CIFAR10average accuracy (%): 88.2 -> 93.1Improved
lower meta learning rate from 1e-4 to 1e-5 (ablation)HLML-SNN · split-CIFAR10average accuracy (%): 93.1 -> 91.2Hurt
add explicit orthogonality constraints (ablation)HLML-SNN · HLML-SNNaccuracy / training time: no gain, 4-fold training timeNo clear effect
use HLML-SNN instead of LWFHLML-SNN vs LWF · split-CIFAR10average accuracy (%): 84.51 -> 93.1Improved
use HLML-SNN instead of LWFHLML-SNN vs LWF · split-MNISTaverage accuracy (%): 99.10 -> 99.1No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy